DAFNE: A Matlab toolbox for Bayesian multi-source remote sensing and ancillary data fusion, with application to flood mapping. (March 2018)

• Record Type: Journal Article
• Authors: D'Addabbo, Annarita; Refice, Alberto; Lovergine, Francesco P.; Pasquariello, Guido
• Is Part Of: Computers & geosciences. Volume 112(2018)
• Page Start: 64
• Page End: 75
• Publication Date: 2018-03
• Subjects: Flood mapping -- Matlab® -- Bayesian networks -- Data fusion; Environmental policy -- Periodicals; 550.5
• DOI: 10.1016/j.cageo.2017.12.005
• Languages: English
• ISSNs: 0098-3004

Abstract

Abstract: High-resolution, remotely sensed images of the Earth surface have been proven to be of help in producing detailed flood maps, thanks to their synoptic overview of the flooded area and frequent revisits. However, flood scenarios can be complex situations, requiring the integration of different data in order to provide accurate and robust flood information. Several processing approaches have been recently proposed to efficiently combine and integrate heterogeneous information sources. In this paper, we introduce DAFNE, a Matlab ® -based, open source toolbox, conceived to produce flood maps from remotely sensed and other ancillary information, through a data fusion approach. DAFNE is based on Bayesian Networks, and is composed of several independent modules, each one performing a different task. Multi-temporal and multi-sensor data can be easily handled, with the possibility of following the evolution of an event through multi-temporal output flood maps. Each DAFNE module can be easily modified or upgraded to meet different user needs. The DAFNE suite is presented together with an example of its application. Highlights: A toolbox to produce flood maps from remotely sensed and other data, is proposed. It is based on Bayesian Networks and is composed of five modules. Multi-temporal and multi-sensor data can be easily handled by the toolbox. It allows to follow the flood dynamics by producing multi-temporal output maps.